© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3694
    Prev
    Next
    INDEX
    Explanations

    evening of, economic justice

    np_acts-logits-general · gemini-2.5-flash-lite

    defining examples, lists, or ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CH
    0.52
     D
    0.51
     in
    0.48
     missp
    0.47
     Categor
    0.46
     Cons
    0.46
    ICATION
    0.46
     Ciò
    0.46
    ጮ
    0.46
     స్వ
    0.45
    POSITIVE LOGITS
    ウト
    0.55
    仕
    0.52
    ਫ਼
    0.52
    タリー
    0.50
    酷
    0.49
    娛樂
    0.48
    owały
    0.47
    ంబేద్కర్
    0.47
    फ्
    0.47
    𝐠
    0.47
    Activations Density 0.000%

    No Known Activations